Correction on Deep Learning Screening of Urothelial Carcinoma
Author Information
Author(s): Tsuneki Masayuki, Abe Makoto, Kanavati Fahdi
Primary Institution: Medmain Research, Medmain Inc.
Conclusion
The correction clarifies that SurePath liquid-based cytology specimens were used instead of ThinPrep, but the scientific conclusions remain unaffected.
Supporting Evidence
- The correction clarifies the type of specimens used in the study.
- The study involved a total of 1556 urine cytology specimens.
- The authors confirmed that cytoscreeners and pathologists could classify the specimens.
Takeaway
The study corrected an error about the type of urine samples used, but the main findings are still valid.
Methodology
The study involved training deep learning models using a dataset of urine liquid-based cytology specimens.
Potential Biases
The reliance on a single laboratory may introduce bias in the findings.
Limitations
The study primarily included specimens from a single private clinical laboratory in Japan.
Participant Demographics
Specimens were collected from a private clinical laboratory in Japan.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website